© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39100
    Prev
    Next
    INDEX
    Explanations

    citation markers like 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vasto
    -1.24
    Ḏ
    -1.05
    ѭ
    -1.03
    haviors
    -1.03
     borgo
    -1.02
    taku
    -0.99
    plik
    -0.99
     laboratorio
    -0.99
    četně
    -0.98
    ︡
    -0.98
    POSITIVE LOGITS
     -
    1.21
    !
    1.02
     !
    1.02
    !'
    0.95
     .
    0.93
    `
    0.92
     \
    0.92
     ("
    0.90
     қара
    0.88
    !)
    0.85
    Activations Density 0.004%

    No Known Activations